Semantic Scale Space: A Framework for Controllable Image Abstraction
Kazu Mishiba
摘要
a) AGSS Abstraction Stages (Color) (b) XDoG on AGSS Abstraction Stages Figure 1. Controlling the abstraction of an input image is key to achieving high-quality stylized results. Our proposed method, AGSS, provides this control at the input level. (a) AGSS applied to a natural photograph: the original image (left) is progressively abstracted to weak (middle) and strong (right) levels, suppressing texture while preserving key structures. (b) XDoG line art applied with fixed parameters to each stage in (a): using the raw photograph as input (left) produces a cluttered result, whereas feeding in weak and strong AGSS bases (middle and right) yields cleaner, more iconic depictions whose level of simplification can be chosen by the user.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper4
- MuGE: Multiple Granularity Edge DetectionCaixia Zhou, Yaping Huang, Mengyang Pu, Qingji Guan 等CVPR 2024 · 被引用 25 次
- Sketch Generation with Drawing Process Guided by Vector Flow and GrayscaleZhengyan Tong, Xuanhong Chen, Bingbing Ni, Xiaohang WangAAAI 2021 · 被引用 24 次
- Deep Flexible Structure Preserving Image SmoothingMingjia Li, Yuanbin Fu, Xinhui Li, Xiaojie GuoACM MM 2022 · 被引用 14 次
- Learning to Cartoonize Using White-Box Cartoon RepresentationsXinrui Wang, Jinze YuCVPR 2020
相关 Paper
- Abstraction in Style: Beyond Texture and ColorMin Lu, Yuanfeng He, Anthony Chen, Jianhuang He 等SIGGRAPH 2026
- CLIPascene: Scene Sketching with Different Types and Levels of AbstractionYael Vinker, Yuval Alaluf, Daniel Cohen-Or, Ariel ShamirICCV 2023 · 被引用 93 次
- One-Shot Structure-Aware Stylized Image SynthesisHansam Cho, Jonghyun Lee, Seunggyu Chang, Yonghyun JeongCVPR 2024
- Interactive Cartoonization with Controllable Perceptual FactorsNamhyuk Ahn, Patrick Kwon, Jihye Back, Kibeom Hong 等CVPR 2023
- Layered Image Vectorization via Semantic SimplificationZhenyu Wang, Jianxi Huang, Zhida Sun, Yuanhao Gong 等CVPR 2025
